Kernel-Distance Target Alignment

摘要：

　　The success of kernel methods are dependent on the kernel,thus a choice of a kernel and proper setting of its parameters are crucial importance.Learning a kernel from the data requires evaluation measures to assess the quality of the kernel.In this paper,we propose a new measure named kernel distance target alignment (KDTA).The measure retains the property of state-of-the-art evaluation measures,kernel target alignment (KTA) and feature space-based kernel matrix evaluation measure (FSM),additionally overcomes the limitation of them.Comparative experiments indicate that the new measure is a good indication of the superiority of a kernel and can get better parameter of RBF kernel.

关键词： kernel methods kernel evaluation measure kernel distance

作者: Peiyan Wang Cai Dongfeng

作者单位: College of Computer Science and Technology,Nanjing University of Aeronautics And Astronautics,Jiangs Knowledge Engineering Research Center,Shenyang Aerospace University,Liaoning Shenyang 110136,China

会议类型: 国际会议

会议名称: Chinese Conference on Pattern Recognition, CCPR(2014年全国模式识别学术会议)

会议地点: 长沙

会议语种:英文

页码: 101-110

在线出版日期: 2014-11-01（万方平台首次上网日期，不代表论文的发表时间）